ClawHub
Back to skill

Security audit

Web3-Crypto-Degen

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed crypto trading helper, but it asks for broad exchange credentials and raw wallet private keys globally, creating avoidable financial risk even for read-only use.

Install only if you intend to use live crypto trading features. Prefer separating read-only analytics from execution, provide only the one provider credential needed for a specific task, use withdrawal-disabled trade-only exchange keys with IP allowlisting, and never use a primary or well-funded wallet private key in this skill.

A.I.G

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:27
Finding

Global Credential Declaration Violates the Principle of Least Privilege

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Findings (13)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 497)May include surrounding context.

text
⚪ Config:     Safe to commit to .env.example as placeholder values
🟡 Sensitive:  Must be in .env (gitignored), contains API keys or RPC endpoints with keys
🔴 Secret:     Must NEVER appear in logs, code, or git history
🔴 Critical:   Private keys — highest security; compromise = total fund loss

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 511)May include surrounding context.

text
⚪ Config:     Safe to commit to .env.example as placeholder values
🟡 Sensitive:  Must be in .env (gitignored), contains API keys or RPC endpoints with keys
🔴 Secret:     Must NEVER appear in logs, code, or git history
🔴 Critical:   Private keys — highest security; compromise = total fund loss

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 520)May include surrounding context.

text
⚪ Config:     Safe to commit to .env.example as placeholder values
🟡 Sensitive:  Must be in .env (gitignored), contains API keys or RPC endpoints with keys
🔴 Secret:     Must NEVER appear in logs, code, or git history
🔴 Critical:   Private keys — highest security; compromise = total fund loss

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 525)May include surrounding context.

text
⚪ Config:     Safe to commit to .env.example as placeholder values
🟡 Sensitive:  Must be in .env (gitignored), contains API keys or RPC endpoints with keys
🔴 Secret:     Must NEVER appear in logs, code, or git history
🔴 Critical:   Private keys — highest security; compromise = total fund loss

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 551)May include surrounding context.

text
⚪ Config:     Safe to commit to .env.example as placeholder values
🟡 Sensitive:  Must be in .env (gitignored), contains API keys or RPC endpoints with keys
🔴 Secret:     Must NEVER appear in logs, code, or git history
🔴 Critical:   Private keys — highest security; compromise = total fund loss

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 597)May include surrounding context.

text
⚪ Config:     Safe to commit to .env.example as placeholder values
🟡 Sensitive:  Must be in .env (gitignored), contains API keys or RPC endpoints with keys
🔴 Secret:     Must NEVER appear in logs, code, or git history
🔴 Critical:   Private keys — highest security; compromise = total fund loss

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 669)May include surrounding context.

text
⚪ Config:     Safe to commit to .env.example as placeholder values
🟡 Sensitive:  Must be in .env (gitignored), contains API keys or RPC endpoints with keys
🔴 Secret:     Must NEVER appear in logs, code, or git history
🔴 Critical:   Private keys — highest security; compromise = total fund loss

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are extremely broad and span discovery, analytics, trading, broadcasting, and meme/speculative workflows. In a user-invocable skill that can access exchange APIs and signing keys, ambiguous triggers increase the chance of accidental invocation or misuse for sensitive financial actions, even if the metadata says auto-triggering is disabled.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 138)May include surrounding context.

md
| API                  | Method | Path                                                                      | Purpose                                   |
| -------------------- | ------ | ------------------------------------------------------------------------- | ----------------------------------------- |
| OKX Search           | GET    | /api/v6/dex/market/token/search?chains=&search=                           | Search by name/symbol/address             |
| OKX Ranking          | GET    | /api/v6/dex/market/token/toplist?chains=&sortBy={2\|5\|6}&timeFrame={1-4} | Rank by change/volume/mcap                |
| OKX Basic Info       | POST   | /api/v6/dex/market/token/basic-info                                       | Batch metadata                            |
| OKX Holders          | GET    | /api/v6/dex/market/token/holder?chainIndex=&tokenContractAddress=         | Top 20 holder distribution                |
| Binance Search       | GET    | bapi/.../market/token/search?keyword=&chainIds=&orderBy=volume24h         | Alternative search source                 |

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · SKILL.md (reported line 221)May include surrounding context.

md
## VII. Domain 5 — DEX Swap Execution

### OKX Aggregator (all GET)
| Endpoint                                                                                    | Purpose                          |
| ------------------------------------------------------------------------------------------- | -------------------------------- |
| /api/v6/dex/aggregator/quote?chainIndex=&fromTokenAddress=&toTokenAddress=&amount=          | Get quote                        |
| /api/v6/dex/aggregator/approve-transaction?chainIndex=&tokenContractAddress=&approveAmount= | ERC20 approval                   |

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 521)May include surrounding context.

md
- Bitget: https://www.bitget.com/account/newapi
          - Alchemy (RPC): https://dashboard.alchemy.com
        → Ask the user to set it in .env
        → NEVER ask the user to paste secrets into chat
Rule 5: For DEPLOYER_PRIVATE_KEY / SOL_PRIVATE_KEY:
        → Recommend generating locally (cast wallet new, solana-keygen new)
        → For mainnet: use hardware wallet or the project Vault system

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · SKILL.md (reported line 662)May include surrounding context.

md
Before activating this skill with live credentials, verify every item below:

| #   | Check                                                                                                                              | Status |
| --- | ---------------------------------------------------------------------------------------------------------------------------------- | ------ |
| 1   | **Testnet first** — `ENABLE_TESTNET=true` tested successfully before mainnet                                                       | ☐      |
| 2   | **Dedicated wallets** — `DEPLOYER_PRIVATE_KEY` / `SOL_PRIVATE_KEY` are fresh wallets with minimal balance, not your primary wallet | ☐      |

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The documented endpoint includes targetLanguage=en, which imposes a specific language choice in natural-language behavior. There is no indication here that the user can choose another language or that English is a justified fixed requirement.

Content

No source excerpt is available for this finding.